Sparse image representation by discrete cosine/spline based dictionaries

09/07/2009

∙

by   James Bowley, et al.

∙

0

∙

share

Mixed dictionaries generated by cosine and B-spline functions are considered. It is shown that, by highly nonlinear approaches such as Orthogonal Matching Pursuit, the discrete version of the proposed dictionaries yields a significant gain in the sparsity of an image representation.